A multi-point contact detection method and system for a contact displacement sensor

By combining multi-point contact displacement sensors with machine learning algorithms, the stress on the suspension system is monitored and analyzed in real time, and a drive compensation model is constructed. This solves the problem of insufficient detection accuracy of single-point contact sensors and achieves more efficient and accurate stress analysis and anomaly detection.

CN123111158APending Publication Date: 2026-11-17SHENZHEN GREAT TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611163583.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-08-03
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Existing single-point contact displacement sensors are insufficient to fully capture the force conditions of a car's suspension system, resulting in inadequate detection accuracy.

Method used

A multi-point contact detection method is adopted, combined with a machine self-learning algorithm, to build a driving compensation model. The displacement data of the contact points is monitored and analyzed in real time by a multi-point contact displacement sensor, generating a detection report and identifying and correcting abnormal detection points.

Benefits of technology

It improves the accuracy and reliability of suspension system detection, enabling timely detection and correction of abnormalities, enhancing vehicle safety and stability, and providing more comprehensive and accurate force information.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123111158A_ABST
    Figure CN123111158A_ABST
Patent Text Reader

Abstract

This invention relates to the field of sensor detection technology, and more particularly to a multi-point contact detection method using a contact displacement sensor. This method utilizes a multi-point contact sensor to acquire precise contact point displacement data, and constructs a driving compensation model through a self-learning algorithm to correct for changes in trajectory data. The application of the sensor improves the accuracy and reliability of detection, helps determine the state of abnormal detection points, and generates accurate detection reports. This application effectively improves the accuracy of contact displacement sensors in detecting suspension systems.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the technical field of sensor detection, and in particular to a multi-point contact detection method and system for a contact displacement sensor. Background Technology

[0002] Sensor technology is widely used in automotive engineering to measure and monitor various physical quantities, such as displacement, pressure, and acceleration. Common sensors include contact displacement sensors, pressure sensors, and acceleration sensors. These sensors can provide crucial data for force analysis and anomaly detection.

[0003] Contact displacement sensors are widely used in automotive engineering to simulate and predict the stress on vehicles under different operating conditions. By establishing physical models and applying numerical methods, the stress distribution and changes of vehicle components such as structure, suspension system, and braking system can be analyzed.

[0004] Existing methods typically use single-point contact sensors to analyze the stress on a car's suspension system. This makes it difficult to fully capture the stress at the contact point, thus reducing the accuracy of contact displacement sensors in detecting the suspension system. Therefore, improvements are needed. Summary of the Invention

[0005] To improve the accuracy of contact displacement sensors in detecting suspension systems, this application provides a multi-point contact detection method and system for contact displacement sensors.

[0006] Firstly, the above-mentioned inventive objective of this application is achieved through the following technical solution:

[0007] A multi-point contact detection method for a contact displacement sensor, the method comprising the following steps:

[0008] Acquire initial detection point data for each contact point to construct an initial detection point model for multi-point contact;

[0009] Acquire initial and real-time detection data for each contact point to calculate displacement data for each contact point;

[0010] A real-time detection model is constructed based on the displacement data of each contact point. The initial detection point model and the real-time detection model are input into a preset three-dimensional coordinate system to record the change data of each contact point.

[0011] Record historical change data of each contact point to construct change trajectory data of each contact point, and compare the change trajectory data of each contact point to determine whether there are abnormal detection points. If there are abnormal detection points, mark the contact points corresponding to the abnormal detection points.

[0012] Acquire the vehicle's driving data and associate the driving data with the change trajectory data corresponding to the anomaly detection points based on a preset time axis to construct a driving-anomaly dataset;

[0013] The driver-anomaly dataset is self-learned based on a machine self-learning algorithm to construct a driver compensation model. The driver compensation model is used to generate detection point driver compensation data caused by the driver. The detection point driver compensation data is used to correct the change trajectory data.

[0014] Based on the detection point-driven compensation data, the trajectory data corresponding to the abnormal detection point is corrected to generate first abnormal correction data, so as to determine whether the corresponding abnormal detection point is in an abnormal state, and a detection report is generated based on the judgment result.

[0015] By adopting the above technical solution, a multi-contact displacement sensor is used to detect the suspension system. Compared with the traditional method of using a single-point contact sensor for force analysis, this solution utilizes a multi-point contact displacement sensor to provide more comprehensive and accurate force information, improving the accuracy of force analysis. Data processing is performed to improve the efficiency and accuracy of data processing. The solution analyzes and corrects the trajectory data of abnormal detection points, improving the accuracy and reliability of anomaly detection. Specifically, this solution uses machine learning algorithms to self-learn the drive-anomaly dataset, constructing a drive compensation model to generate drive compensation data for detection points based on drive factors. This data is used to correct the trajectory data of abnormal detection points. Compared with traditional manual correction methods, self-learning drive compensation can more accurately eliminate abnormal changes caused by drive factors, improving the accuracy and reliability of the data. By acquiring and analyzing the displacement data of contact points in real time, the movement trajectory and changing trends of contact points can be monitored and recorded in real time. Compared with traditional offline analysis methods, real-time monitoring and analysis can provide immediate feedback and diagnosis, helping to identify and solve problems early, and improving the safety and reliability of the vehicle.

[0016] In a preferred embodiment, this application can be further configured to include the following steps during the process of the vehicle's driving state changing from moving to stationary:

[0017] The efficiency of the vehicle's drive change is calculated, with the data at the instant deceleration begins as the initial data for the change in drive data.

[0018] Acquire the detection point data of each contact point at the instant the car comes to a standstill in order to construct a reset detection point model;

[0019] The initial detection point model and the reset detection point model are input into the three-dimensional coordinate system, and the differences between the initial detection point model and the reset detection point model are compared to generate reset difference data corresponding to the driving change efficiency. The reset difference data is used to adjust the initial detection point data after each braking stop during driving.

[0020] By adopting the above technical solution, and by comparing the differences between the initial detection point model and the reset detection point model, the correlation between drive change efficiency and contact point position is analyzed. The generated reset difference data can be used to adjust the initial detection point data after each braking stop during driving, thereby further improving the accuracy and stability of the data.

[0021] In a preferred example, this application can be further configured as follows: after the step of performing self-learning on the driver-anomaly dataset based on a machine self-learning algorithm to construct a driver compensation model, the driver compensation model being used to generate detection point driver compensation data caused by the driver, and the detection point driver compensation data being used to correct the change trajectory data, the application includes the following steps:

[0022] Acquire the vehicle's navigation data and real-time driving data and generate predictive driving change efficiency;

[0023] The driving compensation model generates predictive driving compensation data based on the predicted driving change efficiency, and the predictive driving compensation data is used to determine the predicted abnormal state of each contact point.

[0024] By adopting the above technical solution, predictive drive compensation data is generated based on the predictive drive change efficiency. The predictive drive compensation data can be used to determine the predicted abnormal state of each contact point, that is, whether there are abnormalities in the contact point during the drive process. By using the predictive drive compensation data, abnormal states of contact points can be identified and judged in advance, such as abnormal changes in the suspension system and abnormal tire wear, which helps to take timely measures for correction and maintenance, thereby improving the stability and safety of the vehicle.

[0025] In a preferred example, this application can be further configured to include the following steps after acquiring the vehicle's navigation data and real-time driving data and generating a predicted driving change efficiency:

[0026] The difference in driving efficiency is calculated based on the actual driving efficiency of the vehicle and the predicted driving efficiency, and a difference in driving efficiency dataset is constructed based on the historical difference in driving efficiency.

[0027] The dataset of changes in efficiency is self-learned based on a machine self-learning algorithm to generate driving habit data during driving.

[0028] The predicted drive change efficiency is corrected based on the driving habit data to generate a corrected predicted drive compensation number.

[0029] By employing the aforementioned technical solutions, the driving characteristics and trends under different driving conditions are analyzed. This helps to understand the impact of driving behavior and habits, providing a basis for the subsequent generation and correction of driving habit data. Self-learning is performed based on the change efficiency difference dataset to generate driving habit data during driving. This data allows for a better understanding of driver behavior and habits, providing a basis for subsequent correction of predictive driving compensation data. The predicted driving compensation data is then corrected based on the driving habit data, adjusting its values ​​and trends to better align with the driver's actual driving habits. This correction more accurately reflects the driver's actual needs and habits, improving the accuracy of subsequent contact displacement sensor detection of the suspension. Multi-point contact displacement sensors can acquire displacement data from each contact point, providing more comprehensive and accurate force information, which aids in the generation and correction of driving habit data, and improves the accuracy and reliability of the driving compensation model.

[0030] In a preferred example, this application can be further configured as follows: after recording historical change data of each contact point to construct change trajectory data of each contact point, comparing the change trajectory data corresponding to each contact point to determine whether there are abnormal detection points, and marking the contact points corresponding to the abnormal detection points if they exist, the application includes the following steps:

[0031] Environmental data is acquired and correlated with the change trajectory data corresponding to the anomaly detection points based on the time axis to construct an environment-anomaly dataset;

[0032] The environment-anomaly dataset is self-learned based on a machine self-learning algorithm to construct an environment compensation model. The environment compensation model is used to generate detection point environment compensation data caused by different driving environments. The detection point environment compensation data is used to correct the changed trajectory data.

[0033] The first anomaly correction data is corrected based on the environmental compensation data of the detection point to generate the second correction data, so as to determine whether the corresponding anomaly detection point is in an abnormal state, and a detection report is generated based on the judgment result.

[0034] By adopting the above technical solution and correcting based on the environmental compensation data of the detection point, the state of abnormal detection points can be judged more accurately, and corresponding detection reports can be generated. The accurate data provided by the multi-point contact sensor helps to improve the accuracy of the judgment of abnormal states and enhance the reliability of the detection report.

[0035] In a preferred example, this application can be further configured as follows: after the step of acquiring environmental data and associating the environmental data with the change trajectory data corresponding to the anomaly detection points based on the time axis to construct an environment-anomaly dataset, the following steps are included:

[0036] A mapping relationship is constructed between the change trajectory data, environmental data, and driving data to build a weight calculation dataset;

[0037] The weight calculation dataset is self-learned based on a machine self-learning algorithm to calculate the influence weight values ​​of the environmental data and the driving data on the changing trajectory data, and the changing trajectory data is corrected based on the influence weight values.

[0038] By adopting the above technical solution, the multi-point contact sensor can provide accurate trajectory data of each contact point in these steps, thereby helping to establish accurate mapping relationships and calculate influence weight values. The high precision and multi-point detection capability of the sensor help to understand the changes in the contact points more comprehensively and improve the accuracy of the influence weight of environmental and driving factors on the trajectory changes. This further improves the correction effect of the trajectory change data and enhances the detection accuracy of the entire analysis process.

[0039] In a preferred example, this application may be further configured such that the machine self-learning algorithm includes a decision tree self-learning algorithm and a neural network algorithm.

[0040] Secondly, the above-mentioned inventive objective of this application is achieved through the following technical solutions:

[0041] A multi-point contact detection device for a contact displacement sensor, the device comprising: an initial detection point model construction module, used to acquire initial detection point data of each contact point to construct an initial detection point model for multi-point contact;

[0042] The displacement data calculation module is used to acquire the initial detection data and real-time detection data of each contact point in order to calculate the displacement data of each contact point.

[0043] The real-time detection model construction module constructs a real-time detection model based on the displacement data of each contact point, and inputs the initial detection point model and the real-time detection model into a preset three-dimensional coordinate system to record the change data of each contact point;

[0044] The abnormal detection point judgment module is used to record the historical change data of each contact point to construct the change trajectory data of each contact point, and compare the change trajectory data corresponding to each contact point to determine whether there is an abnormal detection point. If there is an abnormal detection point, the contact point corresponding to the abnormal detection point is marked.

[0045] The drive-anomaly dataset construction module is used to acquire the vehicle's drive data and associate the drive data with the change trajectory data corresponding to the anomaly detection points based on a preset time axis to construct the drive-anomaly dataset.

[0046] The driving compensation model construction module is used to perform self-learning on the driving-abnormal dataset based on the machine self-learning algorithm to construct a driving compensation model. The driving compensation model is used to generate driving compensation data for detection points caused by driving. The driving compensation data for detection points is used to correct the change trajectory data.

[0047] The detection report generation module is used to perform trajectory correction on the change trajectory data corresponding to the abnormal detection point based on the detection point-driven compensation data to generate first abnormal correction data, to determine whether the corresponding abnormal detection point is in an abnormal state, and to generate a detection report based on the judgment result.

[0048] Thirdly, the above-mentioned objectives of this application are achieved through the following technical solutions:

[0049] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the multi-point contact detection method for the contact displacement sensor described above.

[0050] Fourthly, the above-mentioned objectives of this application are achieved through the following technical solutions:

[0051] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the multi-point contact detection method for the contact displacement sensor described above.

[0052] In summary, this application includes at least one of the following beneficial technical effects:

[0053] 1. This solution uses multi-point contact displacement sensors to detect the suspension system. Compared to traditional methods that typically use single-point contact sensors for force analysis, this solution utilizes multi-point contact displacement sensors to provide more comprehensive and accurate force information, improving the accuracy of force analysis. Data processing is then performed to enhance efficiency and accuracy. The solution analyzes and corrects the trajectory data of abnormal detection points, improving the accuracy and reliability of anomaly detection. Specifically, this solution uses machine learning algorithms to self-learn the drive-anomaly dataset, constructing a drive compensation model to generate drive compensation data for detection points based on drive factors. This data is used to correct the trajectory data of abnormal detection points. Compared to traditional manual correction methods, self-learning drive compensation can more accurately eliminate abnormal changes caused by drive factors, improving data accuracy and reliability. By acquiring and analyzing the displacement data of contact points in real time, the movement trajectory and changing trends of contact points can be monitored and recorded in real time. Compared to traditional offline analysis methods, real-time monitoring and analysis can provide immediate feedback and diagnosis, helping to identify and solve problems early, thus improving vehicle safety and reliability.

[0054] 2. By comparing the differences between the initial detection point model and the reset detection point model, the correlation between drive change efficiency and contact point position is analyzed. The generated reset difference data can be used to adjust the initial detection point data after each braking stop during driving, further improving the accuracy and stability of the data.

[0055] 3. Generate predictive drive compensation data based on predictive drive change efficiency. The predictive drive compensation data can be used to determine the predicted abnormal state of each contact point, that is, whether there are abnormalities in the contact point during the drive process. By using the predictive drive compensation data, abnormal states of contact points can be identified and judged in advance, such as abnormal changes in the suspension system and abnormal tire wear, which helps to take timely measures for correction and maintenance, thereby improving the stability and safety of the vehicle.

[0056] 4. Analyzing the driving characteristics and trends under different driving conditions helps to understand the impact of driving behavior and habits, providing a basis for subsequent driving habit data generation and correction. Self-learning is performed based on the change efficiency difference dataset to generate driving habit data during driving. This data allows for a better understanding of driver behavior and habits, providing a basis for subsequent prediction of driving compensation data correction. Based on the driving habit data, the prediction of driving compensation data is corrected, adjusting its values ​​and trends to better match the driver's actual driving habits. This correction more accurately reflects the driver's actual needs and habits, improving the accuracy of subsequent contact displacement sensor detection of the suspension. Multi-point contact displacement sensors can be used to acquire displacement data at each contact point, providing more comprehensive and accurate force information, which helps in the generation and correction of driving habit data, improving the accuracy and reliability of the driving compensation model. Attached Figure Description

[0057] Figure 1 This is a flowchart illustrating the steps of a multi-point contact detection method for a contact displacement sensor according to an embodiment of this application.

[0058] Figure 2 This is a schematic block diagram of a multi-point contact detection device for a contact displacement sensor according to one embodiment of this application;

[0059] Figure 3 This is a schematic diagram of an electronic device according to an embodiment of this application.

[0060] Icon labels:

[0061] 1. Initial detection point model construction module; 2. Displacement data calculation module; 3. Real-time detection model construction module; 4. Abnormal detection point judgment module; 5. Driver-abnormal dataset construction module; 6. Driver compensation model construction module; 7. Detection report generation module. Detailed Implementation

[0062] The present application will be further described in detail below with reference to the accompanying drawings.

[0063] In one embodiment, such as Figure 1 As shown, this application discloses a multi-point contact detection method for a contact displacement sensor, which specifically includes the following steps:

[0064] S10: Obtain the initial detection point data for each contact point to construct the initial detection point model for multi-point contact;

[0065] Specifically, in this embodiment of the application, for the multi-contact displacement sensor in the automotive suspension system, the detection point data of each contact point in the multi-contact displacement sensor is acquired in the initial state (the car is started and the vehicle is not moving). The detection point data includes the relative position and relationship between each contact point. This data is used to construct an initial multi-point contact model. In this embodiment of the application, the multi-point contact model is the overall model of the suspension system.

[0066] By acquiring initial detection point data and constructing an initial detection point model to establish a reference benchmark for subsequent displacement measurement and analysis, it helps to ensure that subsequent displacement data is compared with the initial state in order to detect any anomalies or changes.

[0067] S20: Obtain initial detection data and real-time detection data for each contact point to calculate displacement data for each contact point;

[0068] In this step, by acquiring initial and real-time detection data of the contact points, the displacement data of each contact point can be calculated. For example, by measuring the displacement of the contact points at different time points, the velocity and acceleration of the contact points can be calculated, and thus the displacement data of each contact point can be derived.

[0069] By calculating the displacement data of each contact point, the movement and changes of the contact points are monitored and recorded in real time, which is used to evaluate the working status of the suspension system, the dynamic performance of the vehicle, and the adjustment of suspension system parameters.

[0070] S30: Construct a real-time detection model based on the displacement data of each contact point, and input the initial detection point model and the real-time detection model into a preset three-dimensional coordinate system to record the change data of each contact point;

[0071] The displacement data of each contact point is used to construct a real-time detection model. This model can input the initial detection point model and the real-time detection point model into a preset three-dimensional coordinate system to record the change data of the contact points. By constructing a real-time detection model and recording the change data of the contact points, the motion trajectory and change trend of the contact points can be tracked and analyzed in real time. This helps to detect and identify any abnormalities or abnormal changes, and provides detailed data for subsequent analysis and correction.

[0072] S40: Record the historical change data of each contact point to construct the change trajectory data of each contact point, and compare the change trajectory data corresponding to each contact point to determine whether there are abnormal detection points. If there are abnormal detection points, mark the contact points corresponding to the abnormal detection points.

[0073] Record historical change data for each contact point and construct change trajectory data for each contact point. By comparing the change trajectory data corresponding to each contact point, it is possible to determine whether there are abnormal detection points and mark the abnormal detection points.

[0074] Specifically, during vehicle operation, the displacement trajectory of each detection point should be the same. If there is a change in trajectory data that is different from other contact points, it is judged as an abnormal detection point.

[0075] By recording and analyzing historical changes and trajectory data of contact points, potential anomalies can be identified. This helps in the early detection and resolution of problems, improving vehicle safety and reliability.

[0076] S50: Acquire the vehicle's driving data and associate the driving data with the change trajectory data corresponding to the anomaly detection point based on a preset time axis to construct a driving-anomaly dataset;

[0077] Specifically, this step involves acquiring the vehicle's driving data and correlating it with the trajectory data corresponding to anomaly detection points. This constructs a driving-anomaly dataset, where the driving data describes the vehicle's motion state, and the trajectory data from the anomaly detection points describes the abnormal changes at the contact points. By correlating the driving data with the trajectory data from the anomaly detection points, potential driving factors can be linked to the anomalies. This helps to gain a deeper understanding of the causes and mechanisms of the anomalies and provides guidance for subsequent corrections and improvements.

[0078] S60: The driver-abnormal dataset is self-learned based on a machine self-learning algorithm to construct a driver compensation model;

[0079] Specifically, the driving compensation model is used to generate driving compensation data for detection points caused by driving, and the driving compensation data for detection points is used to correct the changed trajectory data;

[0080] To further explain the drive compensation model in this application, it is first necessary to collect drive data and trajectory data corresponding to anomaly detection points. Drive data may include information such as vehicle acceleration, speed, and steering angle, while trajectory data of anomaly detection points may include data such as displacement, speed, and acceleration of the contact point.

[0081] The collected data undergoes preprocessing, including data cleaning, noise removal, and data alignment. This ensures the accuracy and consistency of the data, providing a reliable data foundation for subsequent analysis and modeling.

[0082] Useful features can be extracted from the driving data and the trajectory data of anomaly detection points. For example, features such as the rate of change of acceleration and steering angular velocity can be extracted from the driving data, and features such as the rate of change of displacement and velocity can be extracted from the anomaly detection point data.

[0083] The change trajectory data of anomaly detection points are labeled as normal or abnormal. This labeling can be based on known anomalies or expert judgment, so that machine learning algorithms can learn and model them.

[0084] Machine learning algorithms (in this embodiment, decision trees, support vector machines, neural networks, etc.) are used to train the driver-anomaly dataset. During training, the model learns the correlation between driving factors and anomaly detection points and generates a driver compensation model.

[0085] To illustrate the analysis process in step S60, let's take a specific data example:

[0086] Driver data:

[0087] Time: [0, 1, 2, 3, 4, 5] (unit: seconds)

[0088] Acceleration: [0, 2, 3, 2, 1, 0] (unit: m / s²)

[0089] Steering angle: [0, 10, 20, 30, 20, 10] (unit: degrees)

[0090] Trajectory data of anomaly detection points:

[0091] Time: [0, 1, 2, 3, 4, 5] (unit: seconds)

[0092] Displacement: [0, 1.5, 4, 6, 5.5, 4] (unit: cm)

[0093] In this example, we use acceleration from the driving data and displacement of anomaly detection points as features. By training a machine learning model, the model can learn the correlation between acceleration and displacement and generate a driving compensation model.

[0094] For example, the model might learn that as acceleration increases, displacement also increases accordingly. Then, when new driving data is input, the model can predict the corresponding driving compensation data based on the driving compensation model. Assuming the new driving data is an acceleration of 4 m / s², the model predicts a driving compensation of 1.5 cm.

[0095] Then, the original displacement data of the abnormal detection points is corrected by combining it with the drive compensation data. In this example, the original displacement data is subtracted from the drive compensation data to obtain the corrected displacement data: Corrected displacement: [0, 0.5, 2.5, 4.5, 4, 2.5] (unit: cm)

[0096] This correction process can eliminate the influence of driving factors on the displacement data of abnormal detection points, enabling more accurate analysis and judgment of abnormal situations.

[0097] The trained driver compensation model can be evaluated using cross-validation or by preserving the dataset. The goal of the evaluation is to determine the model's performance and accuracy to ensure that it can effectively correct for changing trajectory data.

[0098] The trained driver compensation model is used to predict new driver data and generate corresponding driver compensation data for detection points. This compensation data can be applied to the trajectory data of abnormal detection points to correct them and eliminate abnormal changes caused by driving factors.

[0099] S70: Based on the detection point-driven compensation data, the trajectory data corresponding to the abnormal detection point is corrected to generate first abnormal correction data, to determine whether the corresponding abnormal detection point is in an abnormal state, and to generate a detection report based on the judgment result.

[0100] In this step, detection point-driven compensation data is used to correct the trajectory of the change data corresponding to the abnormal detection points. The corrected data is then used to generate first-stage anomaly correction data to determine whether the corresponding abnormal detection point is in an abnormal state, and a detection report is generated based on the determination result.

[0101] By correcting and analyzing the change trajectory data of abnormal detection points, it can be determined whether the abnormal detection points are truly in an abnormal state, and a corresponding detection report can be generated. This helps to promptly identify and resolve potential problems, improving the safety and reliability of vehicles.

[0102] In summary, using multi-contact displacement sensors to detect suspension systems offers a more comprehensive and accurate force analysis compared to traditional methods that typically use single-point contact sensors. This improves the precision of force analysis by providing more comprehensive and accurate force information. Data processing is also improved, increasing efficiency and accuracy. Furthermore, the solution analyzes and corrects the trajectory data of abnormal detection points, enhancing the accuracy and reliability of anomaly detection. Specifically, this solution utilizes machine learning algorithms to self-learn the drive-anomaly dataset, constructing a drive compensation model to generate drive compensation data for detection points based on driving factors. This model corrects the trajectory data of abnormal detection points. Compared to traditional manual correction methods, self-learning drive compensation more accurately eliminates abnormal changes caused by driving factors, improving data accuracy and reliability. By acquiring and analyzing contact point displacement data in real time, the system can monitor and record the movement trajectory and trends of contact points. Compared to traditional offline analysis methods, real-time monitoring and analysis provide immediate feedback and diagnosis, helping to identify and resolve problems early, thus improving vehicle safety and reliability.

[0103] The process of a car changing from a moving state to a stationary state includes the following steps:

[0104] The efficiency of the vehicle's drive change is calculated, with the data at the instant deceleration begins as the initial data for the change in drive data.

[0105] Acquire the detection point data of each contact point at the instant the car comes to a standstill in order to construct a reset detection point model;

[0106] The initial detection point model and the reset detection point model are input into the three-dimensional coordinate system, and the differences between the initial detection point model and the reset detection point model are compared to generate reset difference data corresponding to the driving change efficiency. The reset difference data is used to adjust the initial detection point data after each braking stop during driving.

[0107] To further explain the above steps, assuming the car begins to decelerate during driving, we can use contact displacement sensors to acquire the vehicle's driving data, such as measuring the displacement changes of the wheels. At the moment deceleration begins, the displacement data at this moment is recorded as the initial data for the driving data change value, and the time required to stop is obtained to calculate the driving change efficiency. This can evaluate the car's deceleration performance and the responsiveness of the driving system, and also helps to optimize the car's braking system and improve the smoothness and comfort of driving.

[0108] When the car comes to a complete stop, multi-point contact displacement sensors are used to acquire displacement data at each contact point. These contact points can include the contact points between the wheels and the ground, the contact points of the suspension system, etc. This displacement data is used to construct a reset detection point model, that is, to record the position and displacement information of the contact points in the stationary state, and compare it with the initial detection point model to calculate parameters such as displacement difference and angle difference of the contact points, and generate corresponding reset difference data.

[0109] By comparing the differences between the initial detection point model and the reset detection point model, the correlation between drive change efficiency and contact point position (i.e., the impact of braking action on detection) can be analyzed. The generated reset difference data can be used to adjust the initial detection point data after each braking during driving, further improving the accuracy and stability of the data.

[0110] Following step S60: Self-learning the driver-anomaly dataset based on a machine self-learning algorithm to construct a driver compensation model, which generates driver compensation data for detection points caused by the driver, and which corrects the change trajectory data, the following steps are included:

[0111] S601: Acquires the vehicle's navigation data and real-time driving data and generates a predictive driving change efficiency;

[0112] S602: The driving compensation model generates predictive driving compensation data based on the predicted driving change efficiency, and the predictive driving compensation data is used to determine the predicted abnormal state of each contact point.

[0113] Specifically, by using machine self-learning algorithms, predictive drive compensation data is generated based on the predicted drive change efficiency. This data can be used to determine the predicted abnormal state of each contact point, i.e., whether there are any abnormalities at the contact points during the drive process. By using this data, abnormal states of the contact points can be identified and judged in advance, such as abnormal changes in the suspension system or abnormal tire wear. This helps to take timely measures for correction and maintenance, thereby improving the stability and safety of the vehicle.

[0114] Following step S601: Acquiring the vehicle's navigation data and real-time driving data and generating predicted driving change efficiency, the following steps are included:

[0115] S6011: Calculate the difference in driving efficiency based on the actual driving change efficiency of the vehicle and the predicted driving change efficiency to generate a difference in driving efficiency, and construct a difference in driving efficiency dataset based on the historical difference in driving efficiency.

[0116] S6012: The change efficiency difference dataset is self-learned based on a machine self-learning algorithm to generate driving habit data during driving;

[0117] S6013: Based on the driving habit data, the predicted driving change efficiency is corrected to generate a corrected predicted driving compensation number.

[0118] Furthermore, by calculating the difference between the actual and predicted driving efficiency, a difference in driving efficiency is generated. Based on historical differences in driving efficiency, a difference dataset in driving efficiency is constructed, recording the differences in driving efficiency under different driving conditions. By calculating the difference in driving efficiency and constructing the difference dataset, the driving characteristics and trends under different driving conditions are analyzed. This helps to understand the impact of driving behavior and driving habits, providing a basis for the subsequent generation and correction of driving habit data. Based on the difference dataset in driving efficiency, self-learning is performed to generate driving habit data during driving. By generating driving habit data, the driver's behavior and habits can be better understood, providing a basis for the subsequent correction of predicted driving compensation data. Based on the driving habit data, the predicted driving compensation data is corrected, adjusting the values ​​and trends of the predicted driving compensation data to better match the driver's actual driving habits. By correcting the predicted driving compensation data, the actual needs and habits of the driver can be more accurately reflected. This helps to improve the detection accuracy of the suspension by the subsequent contact displacement sensor. Multi-point contact displacement sensors can be used to obtain displacement data of each contact point, providing more comprehensive and accurate force information, which helps to generate and correct driving habit data, and improves the accuracy and reliability of the driving compensation model.

[0119] After step S40: recording historical change data of each contact point to construct change trajectory data of each contact point, and comparing the change trajectory data corresponding to each contact point to determine whether there are abnormal detection points, and marking the contact points corresponding to the abnormal detection points if they exist, the following steps are included:

[0120] S401: Acquire environmental data and associate the environmental data with the change trajectory data corresponding to the anomaly detection points based on the time axis to construct an environment-anomaly dataset;

[0121] S402: The environment-anomaly dataset is self-learned based on a machine self-learning algorithm to construct an environment compensation model. The environment compensation model is used to generate detection point environment compensation data caused by different driving environments. The detection point environment compensation data is used to correct the changed trajectory data.

[0122] S403: Based on the environmental compensation data of the detection point, the first abnormal correction data is corrected to generate the second correction data, so as to determine whether the corresponding abnormal detection point is in an abnormal state, and a detection report is generated based on the judgment result.

[0123] Specifically, environmental data, such as temperature, humidity, and road conditions, is acquired and correlated with the change trajectory data corresponding to anomaly detection points to construct an environment-anomaly dataset. This dataset helps understand the changes in anomaly detection points under different environmental conditions. By constructing the environment-anomaly dataset and analyzing the performance of anomaly detection points under different environmental conditions, the impact of environmental factors on anomaly detection points can be identified. Multi-point contact sensors can provide more accurate contact point change data, which helps to construct a more precise environment-anomaly dataset and improve the accuracy of environmental compensation models.

[0124] By constructing an environmental compensation model, we can better understand the impact of environmental factors on anomaly detection points and perform environmental compensation on the change trajectory data. The precise data provided by multi-point contact sensors helps the model accurately capture the influence of environmental factors on contact point changes, improving the accuracy of the environmental compensation model. The environmental compensation data from the detection points is used to correct the first anomaly correction data, generating second correction data to determine whether the corresponding anomaly detection point is in an abnormal state, and a detection report is generated based on the judgment result.

[0125] By correcting based on environmental compensation data at the detection points, the state of abnormal detection points can be determined more accurately, and corresponding detection reports can be generated. The accurate data provided by multi-point contact sensors helps to improve the accuracy of judging abnormal states and enhance the reliability of detection reports.

[0126] After step S401: acquiring environmental data and associating the environmental data with the change trajectory data corresponding to the anomaly detection points based on the time axis to construct an environment-anomaly dataset, the following steps are included:

[0127] S4011: Construct the mapping relationship between the change trajectory data, environmental data, and driving data to build a weight calculation dataset;

[0128] S4012: Perform self-learning on the weight calculation dataset based on the machine self-learning algorithm to calculate the influence weight values ​​of the environmental data and the driving data on the changing trajectory data, and correct the changing trajectory data based on the influence weight values.

[0129] Specifically, by calculating and correcting the influence weight values, we can more accurately understand the degree of influence of the environment and driving factors on the trajectory change, and make corresponding corrections to the trajectory change data. This allows the accurate data provided by the multi-point contact sensor to help improve the accuracy of the weight calculation, enhance the sensitivity to the environment and driving factors, and improve the correction effect of the trajectory change data.

[0130] Multi-point contact sensors can provide precise trajectory data of each contact point in these steps, thereby helping to establish accurate mapping relationships and calculate influence weight values. The high precision and multi-point detection capability of the sensors help to understand the changes in the contact points more comprehensively, improve the accuracy of the influence weight of environmental and driving factors on the trajectory, which further improves the correction effect of the trajectory data and enhances the detection accuracy of the entire analysis process.

[0131] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0132] In one embodiment, a multi-point contact detection device for a contact displacement sensor is provided, which corresponds one-to-one with the multi-point contact detection method for a contact displacement sensor described in the above embodiments. For example... Figure 2 As shown, the multi-point contact detection device for the contact displacement sensor includes an initial detection point model construction module 1, which is used to acquire the initial detection point data of each contact point in order to construct the initial detection point model of the multi-point contact.

[0133] The displacement data calculation module 2 is used to acquire the initial detection data and real-time detection data of each contact point in order to calculate the displacement data of each contact point.

[0134] The real-time detection model construction module 3 constructs a real-time detection model based on the displacement data of each contact point, and inputs the initial detection point model and the real-time detection model into a preset three-dimensional coordinate system to record the change data of each contact point;

[0135] The abnormal detection point judgment module 4 is used to record the historical change data of each contact point to construct the change trajectory data of each contact point, and compare the change trajectory data corresponding to each contact point to determine whether there is an abnormal detection point. If there is an abnormal detection point, the contact point corresponding to the abnormal detection point is marked.

[0136] The drive-anomaly dataset construction module 5 is used to acquire the vehicle's drive data and associate the drive data with the change trajectory data corresponding to the anomaly detection point based on a preset time axis to construct the drive-anomaly dataset.

[0137] The driving compensation model construction module 6 is used to perform self-learning on the driving-abnormal dataset based on the machine self-learning algorithm to construct a driving compensation model. The driving compensation model is used to generate detection point driving compensation data caused by the driving, and the detection point driving compensation data is used to correct the change trajectory data.

[0138] The detection report generation module 7 is used to perform trajectory correction on the change trajectory data corresponding to the abnormal detection point based on the detection point drive compensation data to generate first abnormal correction data, to determine whether the corresponding abnormal detection point is in an abnormal state, and to generate a detection report based on the judgment result.

[0139] For specific limitations regarding the multi-point contact detection device for a contact displacement sensor, please refer to the limitations of the multi-point contact detection method for contact displacement sensors mentioned above, which will not be repeated here. Each module in the aforementioned multi-point contact detection device for contact displacement sensors can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware or independently of the processor in the electronic device, or stored in software in the memory of the electronic device, so that the processor can call and execute the operations corresponding to each module.

[0140] In one embodiment, an electronic device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 2 As shown, this electronic device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores the database. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a multi-point contact detection method using a contact displacement sensor.

[0141] In one embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps:

[0142] Acquire initial detection point data for each contact point to construct an initial detection point model for multi-point contact;

[0143] Acquire initial and real-time detection data for each contact point to calculate displacement data for each contact point;

[0144] A real-time detection model is constructed based on the displacement data of each contact point. The initial detection point model and the real-time detection model are input into a preset three-dimensional coordinate system to record the change data of each contact point.

[0145] Record historical change data of each contact point to construct change trajectory data of each contact point, and compare the change trajectory data of each contact point to determine whether there are abnormal detection points. If there are abnormal detection points, mark the contact points corresponding to the abnormal detection points.

[0146] Acquire the vehicle's driving data and associate the driving data with the change trajectory data corresponding to the anomaly detection points based on a preset time axis to construct a driving-anomaly dataset;

[0147] The driver-anomaly dataset is self-learned based on a machine self-learning algorithm to construct a driver compensation model. The driver compensation model is used to generate detection point driver compensation data caused by the driver. The detection point driver compensation data is used to correct the change trajectory data.

[0148] Based on the detection point-driven compensation data, the trajectory data corresponding to the abnormal detection point is corrected to generate first abnormal correction data, so as to determine whether the corresponding abnormal detection point is in an abnormal state, and a detection report is generated based on the judgment result.

[0149] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0150] Acquire initial detection point data for each contact point to construct an initial detection point model for multi-point contact;

[0151] Acquire initial and real-time detection data for each contact point to calculate displacement data for each contact point;

[0152] A real-time detection model is constructed based on the displacement data of each contact point. The initial detection point model and the real-time detection model are input into a preset three-dimensional coordinate system to record the change data of each contact point.

[0153] Record historical change data of each contact point to construct change trajectory data of each contact point, and compare the change trajectory data of each contact point to determine whether there are abnormal detection points. If there are abnormal detection points, mark the contact points corresponding to the abnormal detection points.

[0154] Acquire the vehicle's driving data and associate the driving data with the change trajectory data corresponding to the anomaly detection points based on a preset time axis to construct a driving-anomaly dataset;

[0155] The driver-anomaly dataset is self-learned based on a machine self-learning algorithm to construct a driver compensation model. The driver compensation model is used to generate detection point driver compensation data caused by the driver. The detection point driver compensation data is used to correct the change trajectory data.

[0156] Based on the detection point-driven compensation data, the trajectory data corresponding to the abnormal detection point is corrected to generate first abnormal correction data, so as to determine whether the corresponding abnormal detection point is in an abnormal state, and a detection report is generated based on the judgment result.

[0157] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0158] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0159] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A multi-point contact detection method for a contact displacement sensor, characterized in that, The steps include: obtaining initial detection point data for each contact point to construct an initial detection point model for multi-point contact; Acquire initial and real-time detection data for each contact point to calculate displacement data for each contact point; A real-time detection model is constructed based on the displacement data of each contact point. The initial detection point model and the real-time detection model are input into a preset three-dimensional coordinate system to record the change data of each contact point. Record historical change data of each contact point to construct change trajectory data of each contact point, and compare the change trajectory data of each contact point to determine whether there are abnormal detection points. If there are abnormal detection points, mark the contact points corresponding to the abnormal detection points. Acquire the vehicle's driving data and associate the driving data with the change trajectory data corresponding to the anomaly detection points based on a preset time axis to construct a driving-anomaly dataset; The driver-anomaly dataset is self-learned based on a machine self-learning algorithm to construct a driver compensation model. The driver compensation model is used to generate detection point driver compensation data caused by the driver. The detection point driver compensation data is used to correct the change trajectory data. Based on the detection point-driven compensation data, the trajectory data corresponding to the abnormal detection point is corrected to generate first abnormal correction data, so as to determine whether the corresponding abnormal detection point is in an abnormal state, and a detection report is generated based on the judgment result.

2. The multi-point contact detection method for a contact displacement sensor according to claim 1, characterized in that, When the driving state of a car changes from moving to stationary, the following steps are included: calculating the driving change efficiency of the car, where the data at the instant of deceleration begins is used as the initial data for the driving data change value. Acquire the detection point data of each contact point at the instant the car comes to a standstill in order to construct a reset detection point model; The initial detection point model and the reset detection point model are input into the three-dimensional coordinate system, and the differences between the initial detection point model and the reset detection point model are compared to generate reset difference data corresponding to the driving change efficiency. The reset difference data is used to adjust the initial detection point data after each braking stop during driving.

3. The multi-point contact detection method for a contact displacement sensor according to claim 1, characterized in that, After the step of performing self-learning on the driver-anomaly dataset based on a machine self-learning algorithm to construct a driver compensation model, wherein the driver compensation model is used to generate driver compensation data for detection points caused by the driver, and the driver compensation data for detection points is used to correct the changed trajectory data, the following steps are included: Acquire vehicle navigation data and real-time driving data and generate predictive driving change efficiency; The driving compensation model generates predictive driving compensation data based on the predicted driving change efficiency, and the predictive driving compensation data is used to determine the predicted abnormal state of each contact point.

4. The multi-point contact detection method for a contact displacement sensor according to claim 3, characterized in that, After acquiring the vehicle's navigation data and real-time driving data and generating predicted driving change efficiency, the following steps are included: The difference in driving efficiency is calculated based on the actual driving efficiency of the vehicle and the predicted driving efficiency, and a difference in driving efficiency dataset is constructed based on the historical difference in driving efficiency. The dataset of changes in efficiency is self-learned based on a machine self-learning algorithm to generate driving habit data during driving. The predicted drive change efficiency is corrected based on the driving habit data to generate a corrected predicted drive compensation number.

5. The multi-point contact detection method for a contact displacement sensor according to claim 1, characterized in that, After recording historical change data for each contact point to construct change trajectory data for each contact point, comparing the change trajectory data corresponding to each contact point to determine whether there are abnormal detection points, and marking the contact points corresponding to the abnormal detection points if they exist, the following steps are included: Environmental data is acquired and correlated with the change trajectory data corresponding to the anomaly detection points based on the time axis to construct an environment-anomaly dataset; The environment-anomaly dataset is self-learned based on a machine self-learning algorithm to construct an environment compensation model. The environment compensation model is used to generate detection point environment compensation data caused by different driving environments. The detection point environment compensation data is used to correct the changed trajectory data. The first anomaly correction data is corrected based on the environmental compensation data of the detection point to generate the second correction data, so as to determine whether the corresponding anomaly detection point is in an abnormal state, and a detection report is generated based on the judgment result.

6. The multi-point contact detection method for a contact displacement sensor according to claim 5, characterized in that, After acquiring environmental data and associating the environmental data with the change trajectory data corresponding to the anomaly detection points based on the time axis to construct an environment-anomaly dataset, the following steps are included: A mapping relationship is constructed between the change trajectory data, environmental data, and driving data to build a weight calculation dataset; The weight calculation dataset is self-learned based on a machine self-learning algorithm to calculate the influence weight values ​​of the environmental data and the driving data on the changing trajectory data, and the changing trajectory data is corrected based on the influence weight values.

7. The multi-point contact detection method for a contact displacement sensor according to claim 1, characterized in that, Machine self-learning algorithms include decision tree self-learning algorithms and neural network algorithms.

8. A multi-point contact detection device for a contact displacement sensor, applied to the multi-point contact detection method for a contact displacement sensor as described in any one of claims 1 to 7, characterized in that, It includes an initial detection point model construction module (1), which is used to obtain the initial detection point data of each contact point in order to construct an initial detection point model for multi-point contact; The displacement data calculation module (2) is used to obtain the initial detection data and real-time detection data of each contact point in order to calculate the displacement data of each contact point. The real-time detection model construction module (3) constructs a real-time detection model based on the displacement data of each contact point, and inputs the initial detection point model and the real-time detection model into a preset three-dimensional coordinate system to record the change data of each contact point; The abnormal detection point judgment module (4) is used to record the historical change data of each contact point to construct the change trajectory data of each contact point, and compare the change trajectory data corresponding to each contact point to determine whether there is an abnormal detection point. If there is an abnormal detection point, the contact point corresponding to the abnormal detection point is marked. The drive-abnormal dataset construction module (5) is used to acquire the driving data of the car and associate the driving data with the change trajectory data corresponding to the abnormal detection point based on the preset time axis to construct the drive-abnormal dataset. The driving compensation model construction module (6) is used to perform self-learning on the driving-abnormal dataset based on the machine self-learning algorithm to construct a driving compensation model. The driving compensation model is used to generate detection point driving compensation data caused by driving. The detection point driving compensation data is used to correct the change trajectory data. The detection report generation module (7) is used to perform trajectory correction on the change trajectory data corresponding to the abnormal detection point based on the detection point drive compensation data to generate first abnormal correction data, to determine whether the corresponding abnormal detection point is in an abnormal state, and to generate a detection report based on the judgment result.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of a multi-point contact detection method for a contact displacement sensor as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of a multi-point contact detection method for a contact displacement sensor as described in any one of claims 1 to 7.